@inproceedings{eggleston-etal-2025-bridging,
title = "Bridging the Gap: Leveraging {C}herokee to Improve Language Identification for Endangered {I}roquoian Languages",
author = "Eggleston, Liam Enzo and
Cacioli, Michael P. and
Sarabu, Jatin and
Yang, Ivory and
Zhu, Kevin",
editor = "Estevanell-Valladares, Ernesto Luis and
Picazo-Izquierdo, Alicia and
Ranasinghe, Tharindu and
Mikaberidze, Besik and
Ostermann, Simon and
Gurgurov, Daniil and
Mueller, Philipp and
Borg, Claudia and
{\v{S}}imko, Mari{\'a}n",
booktitle = "Proceedings of the First Workshop on Advancing NLP for Low-Resource Languages",
month = sep,
year = "2025",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2025.lowresnlp-1.1/",
pages = "1--6",
abstract = "Language identification is a foundational task in natural language processing (NLP), yet many Indigenous languages remain entirely unsupported by commercial language identification systems. In this study, we assess the performance of Google LangID on a 5k Cherokee dataset and find that every sentence is classified as ``undetermined'', indicating a complete failure to even misidentify Cherokee as another language. To further explore this issue, we manually constructed the first digitalized Northern Iroquoian dataset, consisting of 120 sentences across five related languages: Onondaga, Cayuga, Mohawk, Seneca, and Oneida. Running these sentences through Google LangID, we examine patterns in its incorrect predictions. To address these limitations, we train a random forest classifier to successfully distinguish between these languages, demonstrating its effectiveness in language identification. Our findings underscore the inadequacies of existing commercial language identification models for Indigenous languages and highlight concrete steps toward improving automated recognition of low-resource languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="eggleston-etal-2025-bridging">
<titleInfo>
<title>Bridging the Gap: Leveraging Cherokee to Improve Language Identification for Endangered Iroquoian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Liam</namePart>
<namePart type="given">Enzo</namePart>
<namePart type="family">Eggleston</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Cacioli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jatin</namePart>
<namePart type="family">Sarabu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivory</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Advancing NLP for Low-Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ernesto</namePart>
<namePart type="given">Luis</namePart>
<namePart type="family">Estevanell-Valladares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alicia</namePart>
<namePart type="family">Picazo-Izquierdo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Ranasinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Besik</namePart>
<namePart type="family">Mikaberidze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Ostermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniil</namePart>
<namePart type="family">Gurgurov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Mueller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Borg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marián</namePart>
<namePart type="family">Šimko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Language identification is a foundational task in natural language processing (NLP), yet many Indigenous languages remain entirely unsupported by commercial language identification systems. In this study, we assess the performance of Google LangID on a 5k Cherokee dataset and find that every sentence is classified as “undetermined”, indicating a complete failure to even misidentify Cherokee as another language. To further explore this issue, we manually constructed the first digitalized Northern Iroquoian dataset, consisting of 120 sentences across five related languages: Onondaga, Cayuga, Mohawk, Seneca, and Oneida. Running these sentences through Google LangID, we examine patterns in its incorrect predictions. To address these limitations, we train a random forest classifier to successfully distinguish between these languages, demonstrating its effectiveness in language identification. Our findings underscore the inadequacies of existing commercial language identification models for Indigenous languages and highlight concrete steps toward improving automated recognition of low-resource languages.</abstract>
<identifier type="citekey">eggleston-etal-2025-bridging</identifier>
<location>
<url>https://aclanthology.org/2025.lowresnlp-1.1/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>1</start>
<end>6</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bridging the Gap: Leveraging Cherokee to Improve Language Identification for Endangered Iroquoian Languages
%A Eggleston, Liam Enzo
%A Cacioli, Michael P.
%A Sarabu, Jatin
%A Yang, Ivory
%A Zhu, Kevin
%Y Estevanell-Valladares, Ernesto Luis
%Y Picazo-Izquierdo, Alicia
%Y Ranasinghe, Tharindu
%Y Mikaberidze, Besik
%Y Ostermann, Simon
%Y Gurgurov, Daniil
%Y Mueller, Philipp
%Y Borg, Claudia
%Y Šimko, Marián
%S Proceedings of the First Workshop on Advancing NLP for Low-Resource Languages
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F eggleston-etal-2025-bridging
%X Language identification is a foundational task in natural language processing (NLP), yet many Indigenous languages remain entirely unsupported by commercial language identification systems. In this study, we assess the performance of Google LangID on a 5k Cherokee dataset and find that every sentence is classified as “undetermined”, indicating a complete failure to even misidentify Cherokee as another language. To further explore this issue, we manually constructed the first digitalized Northern Iroquoian dataset, consisting of 120 sentences across five related languages: Onondaga, Cayuga, Mohawk, Seneca, and Oneida. Running these sentences through Google LangID, we examine patterns in its incorrect predictions. To address these limitations, we train a random forest classifier to successfully distinguish between these languages, demonstrating its effectiveness in language identification. Our findings underscore the inadequacies of existing commercial language identification models for Indigenous languages and highlight concrete steps toward improving automated recognition of low-resource languages.
%U https://aclanthology.org/2025.lowresnlp-1.1/
%P 1-6
Markdown (Informal)
[Bridging the Gap: Leveraging Cherokee to Improve Language Identification for Endangered Iroquoian Languages](https://aclanthology.org/2025.lowresnlp-1.1/) (Eggleston et al., LowResNLP 2025)
ACL